Vulnerability in litellm (CVE-2026-42203)
Summary
Vulnerability in litellm (CVE-2026-42203). Successful exploitation can lead to full system takeover. Exploitable via POST /prompts/test. Mitigation: upgrade to 1.83.7 or later.
Original description
The description as published by the source.
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-42203 has been found in litellm.
Attackers can target a specific entry point like POST /prompts/test over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: 8.8/10.
What to do: upgrade litellm to 1.83.7 or later.
If unsure, ask your IT team or search "litellm CVE-2026-42203" on the vendor's site.
CVE-2026-42203 (litellm) — CWE-1336 / CVSS v3 8.8
Attack vector: remote (network-reachable) / no user interaction
Attack surface: POST /prompts/test
Patched: 1.83.7 — apply immediately
Workaround: 1. Block POST /prompts/test at your reverse proxy or API gateway.
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-1336) exists in litellm. Attackers reach the vulnerable code path via POST /prompts/test.
Check the vendor advisory for the affected versions of litellm. Attack surface: POST /prompts/test.
Severity: High (CVSS 8.8/10). Successful exploitation can lead to full system takeover.
Update to 1.83.7.
Workaround: 1. Block POST /prompts/test at your reverse proxy or API gateway.
Search webserver/proxy logs for unusual POST /prompts/test requests with malformed payloads or SQL meta-characters. Run grep -r 'litellm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'litellm' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
litellmを grep し、稼働しているサービス・バージョンを把握する。 -
2Hunt for indicators of compromise detect
grep 'POST /prompts/test' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /prompts/testへの異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。 -
3Apply temporary workaround mitigate
1. Block `POST /prompts/test` at your reverse proxy or API gateway.パッチが適用されるまでの応急処置として、1. Block
POST /prompts/testat your reverse proxy or API gateway. を実施。回避策の副作用 (機能低下) を確認した上で。 -
4Apply patch patch
Upgrade litellm to 1.83.7ステージング環境で 1.83.7 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスと、Step 2 で見つけた異常検知の続報チェックを含めること。
-
5Post-deployment verification verify
Replay attack against POST /prompts/test on staging to confirm patch closes the vectorパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番では Step 2 と同じログクエリでアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- advisory access.redhat.com
- advisory github.com
- package github.com
- report bugzilla.redhat.com
- web github.com
- web github.com
- web security.access.redhat.com